{"id":"W124170475","doi":"","title":"Discrepancy Between Automatic and Manual Evaluation of Summaries","year":2012,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Automatic summarization; Computer science; Metric (unit); ROUGE; Natural language processing; Information retrieval; Artificial intelligence; Coherence (philosophical gambling strategy); Evaluation methods; Significant difference; Data mining; Statistics; Mathematics; Reliability engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000733181,0.00003719193,0.0000695623,0.00002906513,0.00002386353,0.00002035002,0.0001202321,0.00001752546,0.0000218341],"category_scores_gemma":[0.00004372069,0.00002953348,0.00001049761,0.00004955378,0.00001576732,0.0004410857,0.0001111082,0.00002021117,0.000004490374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009902371,"about_ca_system_score_gemma":0.00001912368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003394266,"about_ca_topic_score_gemma":0.000004072493,"domain_scores_codex":[0.9994025,0.00004881732,0.0001203767,0.00008036119,0.0002490367,0.00009890832],"domain_scores_gemma":[0.9996427,0.00005333631,0.00003578697,0.0001949178,0.00003823492,0.00003498274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[2.015694e-7,0.00001711946,0.2111149,0.00002794092,0.00001400847,4.672544e-8,0.002296502,0.00001587668,0.00004347014,0.1810279,0.00006475833,0.6053773],"study_design_scores_gemma":[0.0001832688,0.00001468245,0.3882858,0.00001365984,0.00002854377,0.000001427454,0.00007021912,0.5929644,0.001016952,0.01723342,0.0001056748,0.00008202823],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6754901,0.0001496346,0.3214434,0.0001688171,0.00006193155,0.00006874015,4.083883e-7,0.00003968896,0.002577294],"genre_scores_gemma":[0.9255434,9.411357e-7,0.07433666,0.00001201671,0.00003852956,0.000003109823,6.862264e-7,0.000001317513,0.00006329724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6052952,"threshold_uncertainty_score":0.120434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06725810240843816,"score_gpt":0.3314334499184848,"score_spread":0.2641753475100466,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}